[3.13] gh-134155: fix AttributeError in email._header_value_parser.get_address (GH...

gh-134155: fix AttributeError in email._header_value_parser.get_address (GH-134194)

Append the defect to defects instead of to the parse tree.
(cherry picked from commit d9cad074d52fe31327429fd81e4d2eeea3dbe35b)

Co-authored-by: Sergey Miryanov <sergey.miryanov@gmail.com>
Co-authored-by: Bénédikt Tran <10796600+picnixz@users.noreply.github.com>
Co-authored-by: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>

diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
index f11fa83d45ed2d39d6631380879ff0664c5b7037..91243378dc04416622bbd0ade23effea6c90f274 100644 (file)
--- a/Lib/email/_header_value_parser.py
+++ b/Lib/email/_header_value_parser.py
@@ -1575,7 +1575,7 @@ def get_dtext(value):
 def _check_for_early_dl_end(value, domain_literal):
     if value:
         return False
-    domain_literal.append(errors.InvalidHeaderDefect(
+    domain_literal.defects.append(errors.InvalidHeaderDefect(
         "end of input inside domain-literal"))
     domain_literal.append(ValueTerminal(']', 'domain-literal-end'))
     return True
@@ -1594,9 +1594,9 @@ def get_domain_literal(value):
         raise errors.HeaderParseError("expected '[' at start of domain-literal "
                 "but found '{}'".format(value))
     value = value[1:]
+    domain_literal.append(ValueTerminal('[', 'domain-literal-start'))
     if _check_for_early_dl_end(value, domain_literal):
         return domain_literal, value
-    domain_literal.append(ValueTerminal('[', 'domain-literal-start'))
     if value[0] in WSP:
         token, value = get_fws(value)
         domain_literal.append(token)

diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py
index 60d4dfccba6f925030214322c1faf910a4f3dc38..64bc3677e87db0fa8044240a8c934e83bc70664c 100644 (file)
--- a/Lib/test/test_email/test__header_value_parser.py
+++ b/Lib/test/test_email/test__header_value_parser.py
@@ -2491,6 +2491,38 @@ class TestParser(TestParserMixin, TestEmailBase):
         self.assertEqual(address.all_mailboxes[0].domain, 'example.com')
         self.assertEqual(address.all_mailboxes[0].addr_spec, '"example example"@example.com')
 
+    def test_get_address_with_invalid_domain(self):
+        address = self._test_get_x(parser.get_address,
+            '<T@[',
+            '<T@[]>',
+            '<T@[]>',
+            [errors.InvalidHeaderDefect,    # missing trailing '>' on angle-addr
+             errors.InvalidHeaderDefect,    # end of input inside domain-literal
+            ],
+            '')
+        self.assertEqual(address.token_type, 'address')
+        self.assertEqual(len(address.mailboxes), 0)
+        self.assertEqual(len(address.all_mailboxes), 1)
+        self.assertEqual(address.all_mailboxes[0].domain, '[]')
+        self.assertEqual(address.all_mailboxes[0].local_part, 'T')
+        self.assertEqual(address.all_mailboxes[0].token_type, 'invalid-mailbox')
+        self.assertEqual(address[0].token_type, 'invalid-mailbox')
+
+        address = self._test_get_x(parser.get_address,
+            '!an??:=m==fr2@[C',
+            '!an??:=m==fr2@[C];',
+            '!an??:=m==fr2@[C];',
+            [errors.InvalidHeaderDefect,    # end of header in group
+             errors.InvalidHeaderDefect,    # end of input inside domain-literal
+            ],
+            '')
+        self.assertEqual(address.token_type, 'address')
+        self.assertEqual(len(address.mailboxes), 0)
+        self.assertEqual(len(address.all_mailboxes), 1)
+        self.assertEqual(address.all_mailboxes[0].domain, '[C]')
+        self.assertEqual(address.all_mailboxes[0].local_part, '=m==fr2')
+        self.assertEqual(address.all_mailboxes[0].token_type, 'invalid-mailbox')
+        self.assertEqual(address[0].token_type, 'group')
 
     # get_address_list
 
@@ -2765,6 +2797,19 @@ class TestParser(TestParserMixin, TestEmailBase):
             )
         self.assertEqual(message_id.token_type, 'message-id')
 
+    def test_parse_message_id_with_invalid_domain(self):
+        message_id = self._test_parse_x(
+            parser.parse_message_id,
+            "<T@[",
+            "<T@[]>",
+            "<T@[]>",
+            [errors.ObsoleteHeaderDefect] + [errors.InvalidHeaderDefect] * 2,
+            [],
+            )
+        self.assertEqual(message_id.token_type, 'message-id')
+        self.assertEqual(str(message_id.all_defects[-1]),
+                         "end of input inside domain-literal")
+
     def test_parse_message_id_with_remaining(self):
         message_id = self._test_parse_x(
             parser.parse_message_id,

diff --git a/Misc/NEWS.d/next/Library/2025-05-18-23-46-21.gh-issue-134152.30HwbX.rst b/Misc/NEWS.d/next/Library/2025-05-18-23-46-21.gh-issue-134152.30HwbX.rst
new file mode 100644 (file)
index 0000000..911a4a5
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2025-05-18-23-46-21.gh-issue-134152.30HwbX.rst
@@ -0,0 +1 @@
+:mod:`email`: Fix parsing of email message ID with invalid domain.